The Missing Piece in Model Editing: A Deep Dive into the Hidden Damage Brought By Model Editing

arXiv:2403.07825v1 Announce Type: new
Abstract: Large Language Models have revolutionized numerous tasks with their remarkable efficacy.However, the editing of these models, crucial for rectifying outdated or erroneous information, often leads to a complex issue known as the ripple effect in the hidden space. This effect, while difficult to detect, can significantly impede the efficacy of model editing tasks and deteriorate model performance.This paper addresses this scientific challenge by proposing a novel evaluation methodology, Graphical Outlier Relation based Assessment(GORA), which quantitatively …

abstract arxiv cs.cl deep dive editing hidden however information issue language language models large language large language models leads ripple space tasks type